Update 2026-07-05: Krea 2 Turbo v2.0 workflow added
PhotoFlow Krea 2 v2.0
Upscaling has been improved in version 2.0. There are now presets for the settings (sampler, scheduler, and denoise settings) . This allows upscaling to be performed in pixel space to achieve upscales with minimal denoising, resulting in smoother backgrounds that closely resemble the original image. In addition, the euler_ancestral_cfg_pp sampler in combination with the linear_quadratic scheduler is now recommended for high image quality. For fast generation, euler_ancestral with simple can still be used. There are also now filters to correct the colors of the final image, which can become flat due to repeated sampling.
⚠️ Note that the latest version 0.27.0 of ComfyUI (July 2027) is required to use the fast int8 models.
Update 2026-07-02: Krea 2 Turbo v1.0 workflow added
PhotoFlow Krea 2 v1.0
Krea 2 Turbo is the new king of realism and is suitable for both SFW and NSFW content. This workflow is simple, super fast, and optimized for realism.
⚠️ Note that the latest version 0.27.0 of ComfyUI (July 2027) is required to use the fast int8 models.
Update 2026-03-30: Qwen-Image-2512 Nunchaku v1.0 workflow added
PhotoFlow Qwen-Image-2512 Nunchaku v1.0
Qwen-Image-2512 offers exceptional prompt comprehension and delivers outstanding output quality. However, this comes at the cost of very long generation times due to the model's size and the large number of processing steps required. A practical solution in this workflow is to use a heavily quantized Nunchaku FP4 version, which maintains surprisingly high quality. When combined with an 8-step Lightning LoRA, generation speed improves dramatically while image quality remains excellent.
⚠️ Nunchaku requires a few additional setup steps. Please follow the instructions provided in the workflow.
Update 2026-03-21: Flux.2 klein 9B v1.1 workflow added
PhotoFlow Flux.2 klein 9B v1.1
Version 1.1 is simply a hotfix that resolves an issue with an incorrect calculation of the tile size in the Refiner step. Additionally, the EasyLoraStack has been replaced by the Power Lora Loader. The group bypass for all additional steps now also takes the previews into account accordingly.
Update 2026-03-04: Flux.2 klein 9B v1.0 workflow added
PhotoFlow Flux.2 klein 9B v1.0
Flux.2 klein 9B is a fast, 4‑step model supporting image generation up to 4 MP. The workflow starts with a recommended 2 MP base image, followed by optional face refinement and SeedVR2 upscaling to 5 MP for added fine detail. A subsequent refinement step removes SeedVR2 artefacts and enables optional upscaling up to 16 MP. A subtle touch of film grain completes the process, enhancing realism.
Update 2025-12-07: Z-Image-Turbo v2.0 workflow added
PhotoFlow Z-Image-Turbo v2.0
Version 2.0 introduces an optional Refiner and FaceDetailer, along with a recommended set of LoRAs designed to enhance photorealism and overall image quality.
⚠️⚠️⚠️
Make sure you're using ComfyUI version 0.3.76 or newer, since earlier versions contained a bug that affected the correct application of Z-Image-Turbo LoRAs.
Also ensure your SeedVR2 node is up to date, as a previous issue causing visual artifacts has been fixed.
⚠️⚠️⚠️
♥️♥️♥️
A huge thank you to all the creators of the LoRAs recommended in version 2.0. Your work makes this level of quality possible!
All images in the gallery were generated using the same set of LoRAs with identical strength settings, so in most cases no additional tweaking is required 🙂.
Special thanks to Danrisi (NiceGirls UltraReal, Lenovo UltraReal), aip0pp (PhotoReal BetterNudes), HackAfterDark (After Dark), DirtMcGirt (psxZStyle - Photography Style Lora), ConflictX (35mm Photo), and oleshevakatya (Movie Wide Angle).
♥️♥️♥️
Update 2025-11-29: Z-Image-Turbo workflow added
PhotoFlow Z-Image-Turbo
Z-Index Turbo is super fast, can generate images in 2 megapixel resolution without upscaling, and focuses on realism, so no LoRAs are required.
Update 2025-11-23: Qwen workflow added
PhotoFlow Qwen
Until now, I had been hesitant to create a workflow for Qwen because, although its image quality is outstanding, the generation times can be very long when aiming for maximum quality. The Lightning LoRA helped reduce waiting times significantly, but using it alone led to a quality drop that didn’t meet my standards. However, by combining multiple LoRAs - including the 8 Steps Lightning LoRA - with a new upscaling process using SeedVR2, I have finally achieved a level of quality that satisfies me.
I have also released a separate workflow dedicated solely to upscaling images using SeedVR2. You can find it here.
Update 2025-10-12: Chroma workflow added
PhotoFlow Chroma HD Flash
After Danrisi released the awesome Lenovo UltraReal LoRA, I gave Chroma another shot because the images looked super promising. And I gotta say, Chroma HD is amazing! Chroma needs about 50 steps in standard mode for awesome results, and even with an RTX 5090, that's too long of a wait for me. Fortunately, there is a Chroma Flash LoRA that achieves great results with just a few steps. With CFG 1.0, the time per step is halved again!
Update 2025-08-23: Wan 2.2/2.1 T2I workflow added
PhotoFlow Wan T2I
Wan 2.1 and Wan 2.2 are video models that can also be used to create high-resolution images. Due to the impressive quality, I decided to create a dedicated workflow for them. Wan 2.2 was released during the development of this workflow. Fortunately, Wan 2.2 is even better and can be used like the Wan 2.1 model, including compatibility with most Wan 2.1 LoRAs. Style LoRAs, in particular, work very well. SageAttention with Triton is supported but not required, and the Lightning LoRA is used to ensure fast generation of high-resolution images. Instructions on how to set up and use the workflow are included within the workflow itself.
PhotoFlow XL
This SDXL ComfyUI workflow has been developed to generate realistic photos with a focus on people.
The version 2.0 is not restricted to the use of the DMD2 Speed LoRA. The workflow works just as well without it ♥️.
The default settings and comments in the workflow are geared towards DMD. Accordingly, you only need to adjust the CFG, sampler, scheduler and steps for a non-DMD use 🙂. These values are a good start for a generation without the DMD LoRA:
KSampler
CFG: 3.5 (2.5 - 5.5)
Sampler: dpmpp_sde_gpu
Scheduler: normal
Steps: 25
FaceDetailer
CFG: 3.5 (2.5 - 5.5)
Sampler: dpmpp_sde_gpu
Scheduler: karras
Steps: 18
Recommended Checkpoints
The following checkpoints are particularly suitable:
SFW
epiCRealism XL: https://civarchive.com/models/277058?modelVersionId=1920523
HelloWorld XL: https://civarchive.com/models/43977/leosams-helloworld-xl
Juggernaut XL: https://civarchive.com/models/133005/juggernaut-xl
RealVisXL 5.0: https://civarchive.com/models/139562?modelVersionId=789646
NSFW
Jib Mix Realistic XL: https://civarchive.com/models/194768?modelVersionId=1809082
DonutsDeliveryMix: https://civarchive.com/models/605283?modelVersionId=1739105
Lustify: https://civarchive.com/models/573152?modelVersionId=1094291
Analog Madness SDXL: https://civarchive.com/models/408483/analog-madness-sdxl-realistic-model
Big Love XL2: https://civarchive.com/models/897413?modelVersionId=1464711
XXX-Ray v1.1: https://civarchive.com/models/1064836?modelVersionId=1305584
NSFW (DMD included)
GonzaLomo (Unity/Real XL DMD): https://civarchive.com/models/1513492/gonzalomo-xlfluxpony
Lustify ENDGAME DMD2: https://civarchive.com/models/573152?modelVersionId=1099200
XXX-Ray DMD2: https://civarchive.com/models/1064836?modelVersionId=1624818
Installation
ComfyUI Manager Installation
https://github.com/ltdrdata/ComfyUI-Manager?tab=readme-ov-file#comfyui-manager
Installation of Missing Nodes
Missing nodes in this workflow are highlighted in red. To install them, open the ComfyUI Manager and click on the “Install Missing Custom Nodes” button.
⚠️‼️ComfyUI-KJNodes needed‼️⚠️
It it may happen that the ComfyUI-KJNodes are not included in the list of missing nodes. Simply install the ComfyUI-KJNodes via ComfyUI Manager > Custom Nodes Manager.
After the installation, restart ComfyUI and refresh the browser page.
Further information and tips on configuration can be found in the workflow in the INFO node.
TL;DR
The workflow was developed and tested with a NVIDIA RTX 4080 (16 GB VRAM) and 96 GB RAM.
Leave a positive review, if you like the workflow 😊.
Description
Krea 2 Turbo text-to-image workflow optimized for quality output and fast generation.
FAQ
Comments (20)
oooh yeah ty for krea update!!!
Krea workflow works fine, but when i switch to euler a pp I get black gen images. Disabling sage doesn't help. And Euler a pp works find in my personal workflow.
Nvm, found out euler a pp doesn't work with conditioning zero out
@cobaltpixiv520 Works on my machine. I guess we have different ComfyUI setups. However, the extra waiting time for these samplers is not worth the potencial benefit in my opinion.
@ai839 Fair enough. I think with realism one might be able to get away with euler / euler a, but when it comes to highly detailed illustrations, those can create nonsense details in the background and the pp variants can really tighten things up. To me the pp variants are always better in quality at the cost of time, and in select cases I'm totally willing to make that tradeoff.
@cobaltpixiv520 Good to know in which scenarios it is a good choice. Thanks for the insights.
@cobaltpixiv520 I played around with euler_ancestral_cfg_pp and you are right, it is a very good sampler! Thanks for the hint. It is such a big improvemt I dedicated a new version 2.0 for it.
@ai839 Can't wait to try it out, your workflows are always so clean
What's the difference between this turbo lora vs the official one? Just the rank?
Yes, I guess. I prefer the output of the rank 256 version. Feel free to use the other one.
hey mate, refiners are good but it f*ck up consistency with adding moles and shits. it's great for single character generation but not so good when using a character lora.
Anyway to fix this?
yeah I know it's details but i'm into details lmao
Do you mean the last Refiner step only? Just skip it and, if necessary, increase the step count in the Upscaler to 10 or 12. If the problem is the step before, skip the Upscale Group and start with your final resolution or you can replace the latent upscale by an image upscale in the Upscale Sampler sub graph to be able to reduce the denoise to something around 0.10 to 0.2 (just guessing). Without the latent upscale you should disconnect the seed value and type in a different seed avoiding artifacts.
@AIVORY3D Version 2.0 just released. I guess this is better regarding consistency. I didn't test with character loras yet.
@ai839 ikr bro i tested it the second it was out, it's absolute cinema; goat
So, in my experience, using creative and details is better for character consistency. I think careful is too restrictive, and do not have enough step and denoise to remove the added pimples/moles/etc.. by the upscaler, to match character lora.
Overall, I have much more satisfying results with details, and much less reiterate to achieve desired output!
Just to share my experience :D
Got it to run for flux - best workflow I ever had. However I cant get it to work with krea2
Missing nodes:
easy compare
easy int
They should be part of "comfyui_fearnworksnodes"
Which got loaded: [INFO] 0.0 seconds: XXXXX\custom_nodes\comfyui_fearnworksnodes
However having a look at the fw_nodes.py those nodes are not contained in it - nor are they in git.
ComfyUI version: 0.27.0
comfyui-frontend-package version: 1.45.20
This results in "Individual Width/Height" in "Start Image Sampler" to fail.
Any ideas? Thanks in advance.
Edit: I grabbed "ComfyUI-Easy-Use" as well, now it works. The error message is confusing then or the manager is pulling the wrong node?
Edit2: deinstalled "comfyui_fearnworksnodes" > still working.
I also noticed that ComfyUI often shows the wrong node name. The missing node is from ComfyUI-Easy-Use: https://github.com/yolain/ComfyUI-Easy-Use
@bailung938 The json-file of the workflow contains wrong data. Sorry for that! In the new released version 2.0 it is correct.
The turbo lora recommended in the flow either isn't trained for raw, which doesn't make sense or it's not in comfyUI format, I get an error on the terminal when using it. So you could use this one instead https://huggingface.co/Comfy-Org/Krea-2/blob/main/loras/krea2_turbo_lora_rank_64_bf16.safetensors
I assume you didn't read the big note IMPORTANT: For ComfyUI, you MUST download the optional Comfy lora instead (see optional downloads above) on the model page: https://civitai.red/models/2727641/krea-2-turbo-lora-256dim?modelVersionId=3066079
Your recommended alternative is the same mentioned in the workflow.